ktblsva commented on code in PR #12649:
URL: https://github.com/apache/hudi/pull/12649#discussion_r1918173778
##########
hudi-spark-datasource/hudi-spark/src/test/scala/org/apache/spark/sql/hudi/procedure/TestClusteringProcedure.scala:
##########
@@ -774,6 +774,50 @@ class TestClusteringProcedure extends
HoodieSparkProcedureTestBase {
}
}
+ test("Test Call show_clustering with limit parameter") {
+ withSQLConf("hoodie.compact.inline" -> "false",
"hoodie.compact.inline.max.delta.commits" -> "1") {
+ withTempDir { tmp =>
+ val tableName = generateTableName
+ val basePath = s"${tmp.getCanonicalPath}/$tableName"
+ val hudiOptions = Map(
+ "hoodie.table.name" -> tableName,
+ "hoodie.datasource.write.table.type" -> "COPY_ON_WRITE",
+ "hoodie.datasource.write.recordkey.field" -> "a",
+ "hoodie.datasource.write.partitionpath.field" -> "a,b,c",
+ "hoodie.clean.automatic" -> "true",
+ "hoodie.metadata.enable" -> "true",
+ "hoodie.clustering.inline" -> "true",
+ "hoodie.clustering.inline.max.commits" -> "1",
+ "hoodie.cleaner.commits.retained" -> "2",
+ "hoodie.datasource.write.operation" -> "insert_overwrite"
+ )
+
+ val data = Seq(
+ (1, 2, 4),
+ (1, 2, 4),
+ (1, 2, 3)
+ )
+ val schema = StructType(Array(
+ StructField("a", IntegerType, true),
+ StructField("b", IntegerType, true),
+ StructField("c", IntegerType, true)
+ ))
+
+ val df =
spark.createDataFrame(spark.sparkContext.parallelize(data).map {
+ case (a, b, c) => Row(a, b, c)
+ }, schema)
+
+ df.write
+ .options(hudiOptions)
+ .format("hudi")
+ .mode("append")
+ .save(s"$basePath")
+
+ assertResult(1)(spark.sql(s"call show_clustering(path =>
'$basePath')").count())
Review Comment:
done
--
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.
To unsubscribe, e-mail: commits-unsubscr...@hudi.apache.org
For queries about this service, please contact Infrastructure at:
us...@infra.apache.org
